[GH-ISSUE #1597] PowerPC #883

Closed
opened 2026-04-12 10:33:04 -05:00 by GiteaMirror · 4 comments
Owner

Originally created by @RealMrCactus on GitHub (Dec 19, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1597

Originally assigned to: @dhiltgen on GitHub.

Is it possible to run this on powerpc

Originally created by @RealMrCactus on GitHub (Dec 19, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1597 Originally assigned to: @dhiltgen on GitHub. Is it possible to run this on powerpc
GiteaMirror added the feature request label 2026-04-12 10:33:04 -05:00
Author
Owner

@technovangelist commented on GitHub (Dec 19, 2023):

I don't think this works today, but we can leave this open to track it in case an update is made to support it in the future. Thanks for being part of this great community.

<!-- gh-comment-id:1863300838 --> @technovangelist commented on GitHub (Dec 19, 2023): I don't think this works today, but we can leave this open to track it in case an update is made to support it in the future. Thanks for being part of this great community.
Author
Owner

@RealMrCactus commented on GitHub (Dec 22, 2023):

I don't think this works today, but we can leave this open to track it in case an update is made to support it in the future. Thanks for being part of this great community.

No problem you can just get like super powerful ibm PPC machines for like 200-400 usd with 10 or more cores so it would make sense to put the ai on it i have access to one with 80

<!-- gh-comment-id:1868126078 --> @RealMrCactus commented on GitHub (Dec 22, 2023): > I don't think this works today, but we can leave this open to track it in case an update is made to support it in the future. Thanks for being part of this great community. No problem you can just get like super powerful ibm PPC machines for like 200-400 usd with 10 or more cores so it would make sense to put the ai on it i have access to one with 80
Author
Owner

@Londo-Mollari commented on GitHub (Jan 24, 2024):

Just to add to this, I have an AC922 with 110 logical CPUs 4x V100 GPUs and having Ollama utilize this would be really nice.

<!-- gh-comment-id:1908069458 --> @Londo-Mollari commented on GitHub (Jan 24, 2024): Just to add to this, I have an AC922 with 110 logical CPUs 4x V100 GPUs and having Ollama utilize this would be really nice.
Author
Owner

@dhiltgen commented on GitHub (Mar 12, 2024):

At this point, we're not planning to add support for PPC, so I'm going to close this ticket. Not only would it require non-trivial build time changes, there's also big/little ending concerns around underlying model structures which would result in ongoing maintenance burden to keep PPC from breaking if we were to add it.

<!-- gh-comment-id:1992126672 --> @dhiltgen commented on GitHub (Mar 12, 2024): At this point, we're not planning to add support for PPC, so I'm going to close this ticket. Not only would it require non-trivial build time changes, there's also big/little ending concerns around underlying model structures which would result in ongoing maintenance burden to keep PPC from breaking if we were to add it.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#883